v0.4 Dev Release
Breaking Changes
- the batch_generator now has an additional params output
- Removed Basic Sigmoid (can be implemented with Basic + transfer_function = sigmoid
New Features
- Curriculum Learning
- get_weights function in RNN
- Add customizability to initializations
Small Bug Fixes / Quality Control
- Add tests
- Fix bugs in Romo
- Make Dale's Law train automatically
- Getting / Saving weights returns the effective weights
- Add better user warnings
Note
This version was never released on pip and is only available here.